h3-blackwell-runtime/tools/poll_qwen38_health_spark.sh
2026-08-20 22:08:52 +07:00

27 lines
727 B
Bash

#!/usr/bin/env bash
set -u
for i in $(seq 0 39); do
status=$(docker ps -a --filter name=qwen38-vllm --format '{{.Status}}')
listening=$(ss -ltnp | grep -c ':8002 ' || true)
if curl -fsS --max-time 5 http://127.0.0.1:8002/health >/tmp/qwen38-health.out 2>/tmp/qwen38-health.err; then
echo "HEALTHY poll=$i status=$status listening=$listening"
docker logs --tail 60 qwen38-vllm
exit 0
fi
if [[ $status != Up* ]]; then
echo "NOT_RUNNING poll=$i status=$status listening=$listening"
docker logs --tail 160 qwen38-vllm
exit 2
fi
echo "poll=$i status=$status listening=$listening"
docker logs --tail 10 qwen38-vllm
sleep 30
done
echo "TIMEOUT"
docker logs --tail 200 qwen38-vllm
exit 1